Instructions to use NS-Studio/Kernel-Logic1.5 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use NS-Studio/Kernel-Logic1.5 with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf NS-Studio/Kernel-Logic1.5:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf NS-Studio/Kernel-Logic1.5:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf NS-Studio/Kernel-Logic1.5:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf NS-Studio/Kernel-Logic1.5:Q4_K_M

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf NS-Studio/Kernel-Logic1.5:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf NS-Studio/Kernel-Logic1.5:Q4_K_M

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf NS-Studio/Kernel-Logic1.5:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf NS-Studio/Kernel-Logic1.5:Q4_K_M

Use Docker

docker model run hf.co/NS-Studio/Kernel-Logic1.5:Q4_K_M

LM Studio
Jan

vLLM

How to use NS-Studio/Kernel-Logic1.5 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "NS-Studio/Kernel-Logic1.5"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "NS-Studio/Kernel-Logic1.5",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/NS-Studio/Kernel-Logic1.5:Q4_K_M

Ollama
How to use NS-Studio/Kernel-Logic1.5 with Ollama:
```
ollama run hf.co/NS-Studio/Kernel-Logic1.5:Q4_K_M
```
Unsloth Desktop

How to use NS-Studio/Kernel-Logic1.5 with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf NS-Studio/Kernel-Logic1.5:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "NS-Studio/Kernel-Logic1.5:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use NS-Studio/Kernel-Logic1.5 with Docker Model Runner:
```
docker model run hf.co/NS-Studio/Kernel-Logic1.5:Q4_K_M
```

Lemonade

How to use NS-Studio/Kernel-Logic1.5 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull NS-Studio/Kernel-Logic1.5:Q4_K_M

Run and chat with the model

lemonade run user.Kernel-Logic1.5-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use NS-Studio/Kernel-Logic1.5 with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf NS-Studio/Kernel-Logic1.5:Q4_K_M

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default NS-Studio/Kernel-Logic1.5:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use NS-Studio/Kernel-Logic1.5 with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf NS-Studio/Kernel-Logic1.5:Q4_K_M

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "NS-Studio/Kernel-Logic1.5:Q4_K_M" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

Kernel Logic 1.5

Kernel Logic 1.5 is a fine-tuned large language model optimized for logical reasoning, mathematics, and code generation tasks. Provided in GGUF (Q4_K_M) format, it is engineered for efficient local inference across standard consumer hardware.

⚙️ Training Hardware & Environment

Trained and quantized using Unsloth on Google Colab (Google Compute Engine backend):

Component	Specification	Usage During Run
GPU	NVIDIA Tesla T4 (16 GB VRAM)	`6.1 GB / 15.0 GB`
System RAM	12.7 GB High-Memory	`6.0 GB / 12.7 GB`
Storage / Disk	112.6 GB Virtual Disk	`72.7 GB / 112.6 GB`
Environment	Ubuntu / Python 3 Runtime	Google Colab Cloud GPU
Framework	Unsloth + Llama.cpp Quantization	Q4_K_M GGUF Export

📊 Benchmark Results

Evaluated on September 17, 2026:

Benchmark	Capability / Task	Score / Accuracy
GSM8k	Mathematical Reasoning	68.0%
HumanEval	Python Code Generation & Problem Solving	57.5%
TruthfulQA	Factual Accuracy & Hallucination Resistance	48.0%
MMLU-Pro	Multi-discipline Academic Understanding	38.0%
Average Score	Overall Performance	52.88%

Average Generation Speed: 14.68 tokens/second

{
  "Kernel Logic 1.5": {
    "evaluated_at": "2026-09-17 13:47:01.356204",
    "mmlu_pro_acc": 38.0,
    "gsm8k_acc": 68.0,
    "humaneval_acc": 57.5,
    "truthfulqa_acc": 48.0,
    "average_score_pct": 52.88,
    "avg_tokens_per_second": 14.68
  }
}

Downloads last month: 68

GGUF

Model size

8B params

Architecture

qwen2

Hardware compatibility

4-bit

Model tree for NS-Studio/Kernel-Logic1.5

Base model

Qwen/Qwen2.5-7B

Finetuned

Qwen/Qwen2.5-7B-Instruct

Quantized

(418)

this model